© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 169102
    Prev
    Next
    INDEX
    Explanations

    Chi-squared goodness of fit test

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    يرين
    0.42
     কাট
    0.41
    گیر
    0.39
     lư
    0.39
     برند
    0.39
    镗
    0.38
     Louis
    0.38
     louis
    0.38
    テル
    0.37
     لج
    0.37
    POSITIVE LOGITS
     goodness
    0.70
     Chi
    0.68
    Chi
    0.63
    chi
    0.61
     χ
    0.61
     chi
    0.60
     Residual
    0.56
    χ
    0.53
    Residual
    0.49
     uniformity
    0.49
    Activations Density 0.012%

    No Known Activations